| 基于动态学习比率BP神经网络的时间序列预测方法 |
| |
| 引用本文： | 丁守銮,王洁贞,胡平.基于动态学习比率BP神经网络的时间序列预测方法[J].中国卫生统计,2002,19(4):194-198. |
| |
| 作者姓名： | 丁守銮 王洁贞 胡平 |
| |
| 作者单位： | 山东大学卫生统计教研室,250012 |
| |
| 基金项目： | 山东省自然科学基金资助课题 (编号Y2 0 0 0C1 9) |
| |
| 摘 要： | 目的 探讨人工神经网络在时间序列资料分析中的应用。方法 利用动态学习比率BP算法以双曲正切函数为功能函数的非线性时间序列预测方法。结果 建立HFRS发病率的两种ANN预测模型，其预测精度远远高于传统方法。结论 BP人工神经网络可以用于疾病发病率或死亡率的预测。
|
| 关 键 词： | BP人工神经网络 非线性时间序列 动态学习比率 发病率 医学统计学 |
Predictive Method of Nonlinear Time Series Based on Dynamic Error Correction Using BP Neural Network |
| |
| Ding Shouluan,Wang Jiezhen,Hu Ping.Health Statistical.Predictive Method of Nonlinear Time Series Based on Dynamic Error Correction Using BP Neural Network[J].Chinese Journal of Health Statistics,2002,19(4):194-198. |
| |
| Authors: | Ding Shouluan Wang Jiezhen Hu PingHealth Statistical |
| |
| Abstract: | Objective To explore predictive method of nonlinear time series based on using BP neural network.Methods Based on dynamic error correction BP using artificial neural network with Hyperbolic Tangent function as activation function and the number of hidden node six.Results Build two kinds of ANN forecast models of HFRS incidence They are better than traditional method on prediction precision.Conclusion BP artificial neural network can be used to forecast for disease incidence or mortality. |
| |
| Keywords: | BP artificial neural network Nonlinear time series Dynamic error corection Disease incidence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
